PPP Loan Program Exploratory Data Analysis
Problem Statement
The $953 billion Paycheck Protection Program was the largest small business relief effort in U.S. history - but who actually received the money? This Power BI dashboard analyzes 11.46 million PPP loans issued in 2020 and 2021 to uncover patterns in loan distribution by business size, age, industry, and geography.
Methodology
Data & Preprocessing
The dataset covers SBA loans granted across the entire nation during 2020 and 2021. It includes vital details like loan amounts, dates, and demographic information of borrowers.
The data was initially provided in individual files, and the first step involved using Python scripts to efficiently read and merge these files into a consolidated dataset. This combined dataset was then utilized to build the dashboards.
Microsoft Power BI was employed to construct the dashboard, allowing the presentation of millions of loans in a single view and enabling end users to quickly comprehend the extensive dataset.
Results
Key Findings
Business Age: Out of approximately 11.46 million loans examined, 89% went to businesses operating for two or more years.
Business Size: 83% of loans were granted to businesses with fewer than 10 employees, consistent with the SBA's small business mandate. The second highest category (10%) went to businesses with fewer than 25 employees.
Loan Issuance Trends: April stands out with significantly higher loan issuance in both years. April 2020 saw the highest volume, followed by April 2021, reflecting the pandemic relief timeline.
Interactive Dashboard
Next Steps
- Analyze loan forgiveness rates by business size and industry
- Compare PPP distribution against pre-pandemic SBA lending patterns
- Investigate geographic disparities in loan access and approval rates